Preprints
Conference & Journal Proceedings
-
A Lyapunov analysis of momentum methods in optimization
Joint with Michael Jordan and Benjamin Recht.
Journal of Machine Learning Research (JMLR). 2021. (to appear)
-
Approximate cross-validation: guarantees for model assessment and selection.
Joint with Lester Mackey and Maximillian Kasy.
International Conference on Artificial Intelligence and Statistics (AISTATS). 2020.
-
The disparate equilibria of algorithmic decision making when individuals invest rationally
Joint with Lydia Liu, Nika Haghtalab, Adam Kalai, Christian Borgs, and Jennifer Chayes.
ACM conference on Fairness, Accountability and Transparency (FAccT). 2020.
-
Accelerating rescaled gradient descent: fast minimization of smooth functions
Joint with Lester Mackey and Andre Wibisono.
Advances in Neural Information Processing Systems (NeurIPS). 2019.
[arXiv] [code]
-
Posteriors, conjugacy, and exponential families for completely random measures
Joint with Tamara Broderick and Michael Jordan.
Bernoulli. 2018.
[arXiv]
-
The marginal value of adaptive methods in machine learning
Joint with Becca Roelofs, Mitchell Stern, Nathan Srebro and Benjamin Recht.
Advances in Neural Information Processing Systems (NeurIPS). 2017.
[arXiv]
-
Breaking locality accelerates block Gauss-Seidel
Joint with Stephen Tu, Shivaram Venkataraman, Alex Gittens, Michael Jordan and Benjamin Recht.
International Conference of Machine Learning (ICML). 2017.
[arXiv]
-
A variational perspective on accelerated methods in optimization
Joint with Andre Wibisono and Michael Jordan.
Proceedings of the National Academy of Science (PNAS). 2016.
-
Streaming, variational, Bayes
Joint with Tamara Broderick, Nicholas Boyd, Andre Wibisono and Michael Jordan.
Advances in Neural Information Processing Systems (NeurIPS). 2014
[arXiv]